CN113390814A - Intelligent component analysis system and method based on metamaterial spectrometer chip - Google Patents
Intelligent component analysis system and method based on metamaterial spectrometer chip Download PDFInfo
- Publication number
- CN113390814A CN113390814A CN202110650451.XA CN202110650451A CN113390814A CN 113390814 A CN113390814 A CN 113390814A CN 202110650451 A CN202110650451 A CN 202110650451A CN 113390814 A CN113390814 A CN 113390814A
- Authority
- CN
- China
- Prior art keywords
- metamaterial
- sample
- light source
- driving circuit
- spectrometer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 34
- 238000000034 method Methods 0.000 title description 24
- 238000001228 spectrum Methods 0.000 claims abstract description 32
- 238000004433 infrared transmission spectrum Methods 0.000 claims abstract description 31
- 239000007788 liquid Substances 0.000 claims description 70
- 239000002086 nanomaterial Substances 0.000 claims description 17
- 239000000203 mixture Substances 0.000 claims description 13
- 238000010801 machine learning Methods 0.000 claims description 12
- 238000001514 detection method Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 11
- 239000000758 substrate Substances 0.000 claims description 9
- 238000012706 support-vector machine Methods 0.000 claims description 8
- 238000004140 cleaning Methods 0.000 claims description 6
- 238000007599 discharging Methods 0.000 claims description 6
- 238000002955 isolation Methods 0.000 claims description 6
- 238000013136 deep learning model Methods 0.000 claims description 3
- 238000002329 infrared spectrum Methods 0.000 abstract description 6
- 210000004027 cell Anatomy 0.000 description 9
- 238000013473 artificial intelligence Methods 0.000 description 6
- 238000013135 deep learning Methods 0.000 description 6
- 239000000463 material Substances 0.000 description 6
- 238000004566 IR spectroscopy Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 4
- 230000003595 spectral effect Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- CSCPPACGZOOCGX-UHFFFAOYSA-N Acetone Chemical compound CC(C)=O CSCPPACGZOOCGX-UHFFFAOYSA-N 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 239000003153 chemical reaction reagent Substances 0.000 description 2
- 238000013145 classification model Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004128 high performance liquid chromatography Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 229910052581 Si3N4 Inorganic materials 0.000 description 1
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 1
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 description 1
- GWEVSGVZZGPLCZ-UHFFFAOYSA-N Titan oxide Chemical compound O=[Ti]=O GWEVSGVZZGPLCZ-UHFFFAOYSA-N 0.000 description 1
- NRTOMJZYCJJWKI-UHFFFAOYSA-N Titanium nitride Chemical compound [Ti]#N NRTOMJZYCJJWKI-UHFFFAOYSA-N 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000002306 biochemical method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 210000005056 cell body Anatomy 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000003989 dielectric material Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000001678 irradiating effect Effects 0.000 description 1
- ORUIBWPALBXDOA-UHFFFAOYSA-L magnesium fluoride Chemical compound [F-].[F-].[Mg+2] ORUIBWPALBXDOA-UHFFFAOYSA-L 0.000 description 1
- 229910001635 magnesium fluoride Inorganic materials 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000002381 microspectrum Methods 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 229910052710 silicon Inorganic materials 0.000 description 1
- 239000010703 silicon Substances 0.000 description 1
- HQVNEWCFYHHQES-UHFFFAOYSA-N silicon nitride Chemical compound N12[Si]34N5[Si]62N3[Si]51N64 HQVNEWCFYHHQES-UHFFFAOYSA-N 0.000 description 1
- 229910052814 silicon oxide Inorganic materials 0.000 description 1
- OGIDPMRJRNCKJF-UHFFFAOYSA-N titanium oxide Inorganic materials [Ti]=O OGIDPMRJRNCKJF-UHFFFAOYSA-N 0.000 description 1
- 210000002700 urine Anatomy 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
- G01N2021/3568—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor applied to semiconductors, e.g. Silicon
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention relates to an intelligent component analysis system based on a metamaterial spectrometer chip, which comprises: the device comprises a singlechip, a light source driving circuit, a light source, a sample storage device and a metamaterial spectrometer chip; the tested sample is placed in the sample storage device; a sample storage device and a metamaterial spectrometer chip are sequentially arranged along the direction of emergent light of the wide-spectrum light source; the single chip microcomputer is connected with the light source driving circuit, the light source driving circuit is connected with the wide-spectrum light source, and the single chip microcomputer is used for controlling the light source driving circuit to drive the wide-spectrum light source; infrared rays emitted by the wide-spectrum light source irradiate the tested sample, and the infrared rays penetrate through the tested sample and are transmitted to the metamaterial spectrometer chip to generate infrared transmission spectrum data; the single chip microcomputer is connected with the metamaterial spectrometer chip and is also used for collecting infrared transmission spectrum data and analyzing component classification and content states of the detected sample according to the infrared transmission spectrum data. The invention realizes the miniaturization of the infrared spectrum analyzer by utilizing the metamaterial spectrum analyzer chip.
Description
Technical Field
The invention relates to the technical field of micro spectrum detection, in particular to an intelligent component analysis system and method based on a metamaterial spectrometer chip.
Background
In the conventional method, the test paper method can only carry out semi-quantitative measurement on the components such as acetone and the like in the detected object; biochemical methods require large reagent consumption, waste of time and labor, high pollution and high price; although the high performance liquid chromatography can realize quantitative measurement, the high performance liquid chromatography is long in time consumption and high in cost, is not suitable for the requirement of real-time detection, and can record results only by manual intervention to a certain extent during component analysis. The infrared spectroscopy method does not need any reagent, has low cost, high reliability, high speed, small sample amount, no pretreatment and no pollution, can obtain a plurality of analytes from one detection, does not damage the sample, can repeatedly use the sample, is suitable for on-line and large-scale repeated measurement, can adapt to the application of collecting basic data in large-scale general investigation, and is a very promising component analysis method. However, the infrared intelligent component analyzer designed by using the infrared spectroscopy has the problems of large equipment volume and large mass.
On the other hand, the current artificial intelligence technology still faces various problems in different aspects, especially on substance detection component analysis. One of the problems is that the data acquisition difficulty of the basic layer is high, and the artificial intelligence product needs to judge the project after summarizing and summarizing a large amount of detection data. Abundant detection data can improve the prediction accuracy of artificial intelligence products and promote the continuous iteration and upgrading of artificial intelligence. Having a large-scale, labeled detection database is a necessary condition for artificial intelligence applications to actually fall to the ground. However, the detection data labeling professional degree is high, the acquisition difficulty is high, and the detection data labeling cost and the data acquisition difficulty are increased by the process.
Therefore, how to design a miniaturized and intelligent portable infrared intelligent component analyzer becomes a problem to be solved urgently.
Disclosure of Invention
The invention aims to provide an intelligent component analysis system and method based on a metamaterial spectrometer chip, which can realize the miniaturization and the intellectualization of an infrared spectrum component analyzer.
In order to achieve the purpose, the invention provides the following scheme:
an intelligent composition analysis system based on a metamaterial spectrometer chip, the system comprising: the system comprises a singlechip, a light source driving circuit, a wide-spectrum light source, a sample storage device and a metamaterial spectrometer chip;
a tested sample is placed in the sample storage device;
the sample storage device and the metamaterial spectrometer chip are sequentially arranged along the direction of emergent light of the wide-spectrum light source;
the single chip microcomputer is connected with the light source driving circuit, the light source driving circuit is connected with the wide-spectrum light source, and the single chip microcomputer is used for controlling the light source driving circuit to drive the wide-spectrum light source;
infrared rays emitted by the wide-spectrum light source irradiate the tested sample, the infrared rays penetrate through the tested sample and are transmitted to the metamaterial spectrometer chip, and the metamaterial spectrometer chip detects infrared transmission spectrum data;
the single chip microcomputer is connected with the metamaterial spectrometer chip and is further used for collecting the infrared transmission spectrum data and analyzing the component classification and content state of the detected sample according to the infrared transmission spectrum data.
Optionally, the single chip microcomputer comprises data processing and analyzing software;
and the data processing and analyzing software is used for determining the component classification and content state of the tested sample by an intelligent prediction model.
Optionally, the metamaterial spectrometer chip comprises, in order from top to bottom: the device comprises an isolation protection layer, a metamaterial chip and a detector layer.
Optionally, the metamaterial chip comprises a nanostructure array and a substrate;
the nanostructure array comprises a plurality of nanostructure units arranged in an array;
a plurality of the nanostructure elements are disposed on the substrate.
Optionally, the sample storage device comprises a sample cell, a liquid inlet device and a liquid discharge device;
the top surface of the sample cell is provided with an opening for placing a sample to be detected during detection;
the liquid inlet device is arranged at the top of the side surface of the sample pool and is used for discharging liquid for cleaning the sample pool;
the liquid discharge device is arranged at the bottom of the side surface and used for discharging liquid in the sample cell.
Optionally, the system further comprises a liquid inlet driving circuit and a liquid discharge driving circuit;
the single chip microcomputer is connected with the liquid inlet driving circuit, the liquid inlet driving circuit is connected with the liquid inlet device, and the single chip microcomputer is used for driving the liquid inlet driving circuit to discharge liquid for cleaning the sample pool into the liquid inlet device;
the single chip microcomputer is connected with the liquid drainage driving circuit, the liquid drainage driving circuit is connected with the liquid drainage device, and the single chip microcomputer is further used for driving the liquid drainage driving circuit to enable the liquid drainage device to drain liquid in the sample cell.
Optionally, the system further comprises a prompting device;
the prompting device is connected with the single chip microcomputer and used for displaying the component classification and content state of the tested sample.
A smart composition analysis method based on a metamaterial spectrometer chip, which is applied to a smart composition analysis system based on the metamaterial spectrometer chip, and comprises the following steps:
establishing an intelligent prediction model for carrying out component classification and content determination on the detected sample according to the infrared transmission spectrum data;
acquiring infrared light emitted by a wide-spectrum light source, irradiating the current sample to be detected, transmitting the infrared light to a metamaterial spectrometer chip, and detecting infrared transmission spectrum data corresponding to the current sample to be detected by the metamaterial spectrometer chip;
and inputting the acquired infrared transmission spectrum data corresponding to the current tested sample into the intelligent prediction model, and determining the component classification and content state of the current tested sample.
Optionally, the intelligent prediction model includes a machine learning model and/or a deep learning model, and after the model is subjected to big data training on a large number of various liquid components and spectral signals corresponding to the liquid components, the corresponding liquid component classification and content states can be calculated according to the spectral signals obtained through testing.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention provides an intelligent component analysis system based on a metamaterial spectrometer chip, which comprises: the device comprises a singlechip, a light source driving circuit, a wide-spectrum light source, a sample storage device and a metamaterial spectrometer chip, wherein a sample to be detected is placed in the sample storage device; the sample storage device and the metamaterial spectrometer chip are sequentially arranged along the direction of emergent light of the wide-spectrum light source; the single chip microcomputer is connected with the light source driving circuit, the light source driving circuit is connected with the wide-spectrum light source, and the single chip microcomputer is used for controlling the light source driving circuit to drive the wide-spectrum light source; infrared rays emitted by the wide-spectrum light source irradiate the tested sample, and the infrared rays penetrate through the tested sample and are transmitted to the metamaterial spectrometer chip to generate infrared transmission spectrum data; the single chip microcomputer is connected with the metamaterial spectrometer chip and is further used for collecting the infrared transmission spectrum data and analyzing the component classification and content state of the detected sample according to the infrared transmission spectrum data. The invention realizes the miniaturization of the infrared spectrum analyzer by utilizing the metamaterial spectrum analyzer chip.
The invention also provides an intelligent component analysis method based on the metamaterial spectrometer chip, which comprises the following steps: establishing an intelligent prediction model for carrying out component classification and content determination on the detected sample according to the infrared transmission spectrum data; acquiring infrared transmission spectrum data corresponding to a current sample to be detected, which is generated after infrared light emitted by a wide-spectrum light source irradiates the current sample to be detected and is transmitted to a metamaterial spectrometer chip; and inputting the acquired infrared transmission spectrum data corresponding to the current detected sample into the intelligent prediction model, and determining the component classification and content state of the current detected sample. According to the invention, by establishing the intelligent prediction model, the infrared transmission spectrum data corresponding to the detected sample can be analyzed, so that the intellectualization of the infrared spectrum analyzer is realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a schematic structural diagram of an intelligent component analysis system based on a metamaterial spectrometer chip provided by the invention;
fig. 2 is a flowchart of an intelligent component analysis method based on a metamaterial spectrometer chip provided by the invention.
Description of the symbols:
the system comprises a single chip microcomputer 1, a light source driving circuit 2, a wide-spectrum light source 3, a liquid inlet driving circuit 4, a liquid discharge driving circuit 5, a sample storage device 6, a metamaterial spectrometer chip 7 and a prompting device 8.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide an intelligent component analysis system and method based on a metamaterial spectrometer chip so as to achieve the purposes of miniaturization and intelligence of an infrared spectrum component analyzer.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
As shown in fig. 1, an intelligent composition analysis system based on a metamaterial spectrometer chip, the system comprising: the device comprises a singlechip 1, a light source driving circuit 2, a wide-spectrum light source 3, a sample storage device 6 and a metamaterial spectrometer chip 7; a sample to be tested is placed in the sample storage device 6; the sample storage device 6 and the metamaterial spectrometer chip 7 are sequentially arranged along the direction of emergent light of the wide-spectrum light source 3; the single chip microcomputer 1 is connected with the light source driving circuit 2, the light source driving circuit 2 is connected with the wide-spectrum light source 3, and the single chip microcomputer 1 is used for controlling the light source driving circuit 2 to drive the wide-spectrum light source 3; infrared rays emitted by the wide-spectrum light source 3 irradiate the tested sample, and the infrared rays penetrate through the tested sample and are transmitted to the metamaterial spectrometer chip 7 to generate infrared transmission spectrum data; the single chip microcomputer 1 is connected with the metamaterial spectrometer chip 7, and the single chip microcomputer 1 is further used for collecting the infrared transmission spectrum data and analyzing the component classification and content state of the detected sample according to the infrared transmission spectrum data.
The sample to be tested includes, but is not limited to, urine, blood, and liquids thereof or substances that can be dissolved into liquids.
The single chip microcomputer 1 comprises data processing and analyzing software; the data processing and analyzing software is used for an intelligent prediction model to determine the component classification and content state of the tested sample.
The data processing and analyzing software is burnt into the single chip microcomputer 1 to reduce the volume of the whole system as much as possible, and the data processing and analyzing software has the capability of processing data firstly and then carrying out analysis and judgment according to the processing result.
The metamaterial spectrometer chip 7 comprises the following components in sequence from top to bottom: the device comprises an isolation protection layer, a metamaterial chip and a detector layer.
The metamaterial chip comprises a nanostructure array and a substrate; the nanostructure array comprises a plurality of nanostructure units arranged in an array; a plurality of the nanostructure elements are disposed on the substrate.
The metamaterial spectrometer chip 7 is composed of an isolation protection layer, a metamaterial chip and a detector layer, wherein the isolation protection layer is made of materials which need to be highly transparent in a wave band designed by the system and used for protecting the metamaterial chip, and the metamaterial chip is composed of a nano structure and a substrate, so that the metamaterial spectrometer chip 7 is small in structure, and light rays reach the detector layer through the high-transparency isolation protection layer and the metamaterial chip. The detector layer uses an infrared camera.
The nano structure of the metamaterial chip is a full-dielectric material, such as silicon, titanium oxide, silicon nitride, titanium nitride and the like, the real part of the refractive index of the material is higher than that of the substrate material, and the imaginary part of the material needs to be as small as possible; the substrate material may be any material that can achieve high transmission efficiency in the infrared band, such as silicon oxide and magnesium fluoride.
Gaps can be formed between units of the metamaterial chip nano-structure array or between units of the metamaterial chip nano-structure array, and gaps can be avoided; the shape and size of the nano structure can be square, triangular, spherical, cylindrical and the like, and can be optimized and adjusted according to needs.
The sample storage device 6 comprises a sample pool, a liquid inlet device and a liquid discharge device; the top surface of the sample cell is provided with an opening for placing a sample to be detected during detection; the liquid inlet device is arranged at the top of the side surface of the sample pool and is used for discharging liquid for cleaning the sample pool; the liquid discharge device is arranged at the bottom of the side surface and used for discharging liquid in the sample cell.
Big-end-up model can be considered in the design of sample cell body, can conveniently arrange the residual liquid to the greatest extent like this, and the upper end design of sample cell makes things convenient for the sample to put into for the open mode.
The system also comprises a liquid inlet driving circuit 4 and a liquid discharge driving circuit 5; the single chip microcomputer 1 is connected with the liquid inlet driving circuit 4, the liquid inlet driving circuit 4 is connected with the liquid inlet device, and the single chip microcomputer 1 is used for driving the liquid inlet driving circuit 4 to discharge liquid for cleaning the sample pool into the liquid inlet device; the single chip microcomputer 1 is connected with the liquid discharge driving circuit 5, the liquid discharge driving circuit 5 is connected with the liquid discharge device, and the single chip microcomputer 1 is further used for driving the liquid discharge driving circuit 5 to enable the liquid discharge device to discharge liquid in the sample cell.
After each test, the single chip microcomputer 1 controls the sample cell to automatically clean through the liquid inlet driving circuit 4 and the liquid discharge driving circuit 5. And the automatic blank comparison test is completed. And the accuracy of the next test result is ensured.
The system further comprises a prompting device 8; and the prompting device 8 is connected with the singlechip 1 and is used for displaying the component classification and content state of the tested sample.
As shown in fig. 2, an intelligent composition analysis method based on a metamaterial spectrometer chip is applied to an intelligent composition analysis system based on a metamaterial spectrometer chip, and the method includes: establishing an intelligent prediction model for classifying the tested samples according to the infrared transmission spectrum data; acquiring infrared transmission spectrum data corresponding to a current sample to be detected, which is generated after infrared light emitted by the wide-spectrum light source 3 irradiates the current sample to be detected and is transmitted to the metamaterial spectrometer chip 7; and inputting the acquired infrared transmission spectrum data corresponding to the current detected sample into the intelligent prediction model, and determining the component classification and content state of the current detected sample.
The intelligent prediction model comprises a machine learning model and/or a deep learning model.
The machine learning model employs a support vector machine model that includes a linear kernel, a polynomial kernel, and a gaussian kernel.
The intelligent prediction model comprises two technical routes of traditional machine learning and deep learning. Conventional machine learning methods typically include two steps of feature extraction and classification. The characteristic extraction process can deeply know the characteristics of the data and is beneficial to the physical explanation of the data. And no matter the feature extraction or classification mathematical model has definite mathematical or geometric significance, so that compared with deep learning, the traditional machine learning method has more advantages in classification or identification interpretability.
After the features are extracted, a classification model is established in the feature space to realize the classification of the near infrared spectrum data. The Support Vector Machine (SVM) is a binary model, the most basic model defines a linear classifier with the largest interval in a feature space, and the nonlinear classification capability is provided by a kernel technique, namely by providing dimensions. In many infrared spectral classification documents, SVMs have been shown to perform better than other traditional machine learning models, such as KNN, decision trees, and the like. The method adopts a soft interval maximization SVM, and adopts three kernel techniques of a linear kernel, a polynomial kernel and a Gaussian kernel respectively, so that the problem that training data is linear and inseparable can be solved, and simultaneously, the SVM is compared with methods such as KNN and decision trees, and finally a classification model suitable for the project is determined.
Deep learning is a branch of machine learning, and particularly refers to an artificial neural network architecture using multiple hidden layers. The method integrates feature extraction and feature classification, can automatically learn proper features from data without manually designing the features, and has shown strong performance on spectrum identification. Compared with the traditional machine learning method, the deep learning method has stronger feature expression and classification capability, but due to the general processing process of a black box, the model is not intuitive to human in geometric or physical interpretability, but when the spectral data with unobvious features are aimed at, the deep learning method has better adaptivity and accuracy. The invention realizes the project task by adopting a deep learning method while adopting the traditional machine learning route.
Before establishing an intelligent prediction model for classifying the tested sample according to the infrared transmission spectrum data, the method further comprises the following steps: preprocessing the infrared transmission spectrum data; the preprocessing process comprises the steps of sequentially carrying out dimension reduction, filtering, noise reduction, classification solution mixing and standardization on the infrared transmission spectrum data.
Based on the basic principle of infrared spectroscopy component analysis, the hardware and software systems of the infrared spectroscopy component analyzer are researched from the aspects of internet of things and artificial intelligence base layer data collection, an intelligent and chip portable infrared component analyzer is developed, detected substance component data is collected, conditions can be created for infrared spectroscopy component analysis, and a road is paved for a highly integrated component analyzer. Meanwhile, the method provides reference for the infrared analysis technology in the fields of clinical biomedicine, families and other application.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (10)
1. An intelligent composition analysis system based on a metamaterial spectrometer chip, the system comprising: the system comprises a singlechip, a light source driving circuit, a wide-spectrum light source, a sample storage device and a metamaterial spectrometer chip;
a tested sample is placed in the sample storage device;
the sample storage device and the metamaterial spectrometer chip are sequentially arranged along the direction of emergent light of the wide-spectrum light source;
the single chip microcomputer is connected with the light source driving circuit, the light source driving circuit is connected with the wide-spectrum light source, and the single chip microcomputer is used for controlling the light source driving circuit to drive the wide-spectrum light source;
infrared rays emitted by the wide-spectrum light source irradiate the tested sample, and the infrared rays penetrate through the tested sample and are transmitted to the metamaterial spectrometer chip to generate infrared transmission spectrum data;
the single chip microcomputer is connected with the metamaterial spectrometer chip and is further used for collecting the infrared transmission spectrum data and analyzing the component classification and content state of the detected sample according to the infrared transmission spectrum data.
2. The intelligent component analysis system based on the metamaterial spectrometer chip as claimed in claim 1, wherein the single chip microcomputer comprises data processing and analyzing software;
and the data processing and analyzing software is used for determining the component classification and content state of the tested sample by adopting an intelligent prediction model.
3. The intelligent composition analysis system based on metamaterial spectrometer chips as claimed in claim 1, wherein the metamaterial spectrometer chip comprises in order from top to bottom: the device comprises an isolation protection layer, a metamaterial chip and a detector layer.
4. The intelligent composition analysis system based on metamaterial spectrometer chip as claimed in claim 3, wherein the metamaterial chip comprises a nanostructure array and a substrate;
the nanostructure array comprises a plurality of nanostructure units arranged in an array;
a plurality of the nanostructure elements are disposed on the substrate.
5. The intelligent component analysis system based on the metamaterial spectrometer chip as claimed in claim 1, wherein the sample storage device comprises a sample cell, a liquid inlet device and a liquid discharge device;
the top surface of the sample cell is provided with an opening for placing a sample to be detected during detection;
the liquid inlet device is arranged at the top of the side surface of the sample pool and is used for discharging liquid for cleaning the sample pool;
the liquid discharge device is arranged at the bottom of the side surface and used for discharging liquid in the sample cell.
6. The intelligent composition analysis system based on the metamaterial spectrometer chip as claimed in claim 5, wherein the system further comprises a liquid inlet driving circuit and a liquid discharge driving circuit;
the single chip microcomputer is connected with the liquid inlet driving circuit, the liquid inlet driving circuit is connected with the liquid inlet device, and the single chip microcomputer is used for driving the liquid inlet driving circuit to discharge liquid for cleaning the sample pool into the liquid inlet device;
the single chip microcomputer is connected with the liquid drainage driving circuit, the liquid drainage driving circuit is connected with the liquid drainage device, and the single chip microcomputer is further used for driving the liquid drainage driving circuit to enable the liquid drainage device to drain liquid in the sample cell.
7. The intelligent composition analysis system based on the metamaterial spectrometer chip as claimed in claim 2, wherein the system further comprises a prompting device;
the prompting device is connected with the single chip microcomputer and used for displaying the component classification and content state of the tested sample.
8. An intelligent component analysis method based on a metamaterial spectrometer chip, which is applied to the intelligent component analysis system based on the metamaterial spectrometer chip as claimed in any one of claims 1 to 7, and comprises the following steps:
establishing an intelligent prediction model for analyzing the tested sample according to the infrared transmission spectrum data;
acquiring infrared transmission spectrum data corresponding to a current sample to be detected, which is generated after infrared light emitted by a wide-spectrum light source irradiates the current sample to be detected and is transmitted to a metamaterial spectrometer chip;
and inputting the acquired infrared transmission spectrum data corresponding to the current detected sample into the intelligent prediction model, and determining the component classification and content state of the current detected sample.
9. The intelligent composition analysis method based on a metamaterial spectrometer chip as claimed in claim 8, wherein the intelligent prediction model comprises a machine learning model and/or a deep learning model.
10. The intelligent composition analysis method based on the metamaterial spectrometer chip as claimed in claim 9, wherein the machine learning model employs a support vector machine model, the support vector machine model comprising a linear kernel, a polynomial kernel and a gaussian kernel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110650451.XA CN113390814A (en) | 2021-06-10 | 2021-06-10 | Intelligent component analysis system and method based on metamaterial spectrometer chip |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110650451.XA CN113390814A (en) | 2021-06-10 | 2021-06-10 | Intelligent component analysis system and method based on metamaterial spectrometer chip |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113390814A true CN113390814A (en) | 2021-09-14 |
Family
ID=77620419
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110650451.XA Pending CN113390814A (en) | 2021-06-10 | 2021-06-10 | Intelligent component analysis system and method based on metamaterial spectrometer chip |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113390814A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023224859A1 (en) * | 2022-05-16 | 2023-11-23 | The Regents Of The University Of California | Neural network enabled disease spectroscopy |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107045637A (en) * | 2016-12-16 | 2017-08-15 | 中国医学科学院生物医学工程研究所 | A kind of blood species identification instrument and recognition methods based on spectrum |
| CN108444946A (en) * | 2018-05-10 | 2018-08-24 | 苏州农业职业技术学院 | A kind of Practice for Pesticide Residue in Agricultural Products detection method and device |
| WO2019206430A1 (en) * | 2018-04-27 | 2019-10-31 | Ecole Polytechnique Federale De Lausanne (Epfl) | Method and spectrometer apparatus for investigating an infrared absorption of a sample |
| CN111426636A (en) * | 2020-04-09 | 2020-07-17 | 米诺杰科技(江苏)有限公司 | Instrument for quickly analyzing chemical component content of wine |
| US20210025813A1 (en) * | 2018-03-16 | 2021-01-28 | Keio University | Infrared analysis system, infrared analysis chip, and infrared imaging device |
-
2021
- 2021-06-10 CN CN202110650451.XA patent/CN113390814A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107045637A (en) * | 2016-12-16 | 2017-08-15 | 中国医学科学院生物医学工程研究所 | A kind of blood species identification instrument and recognition methods based on spectrum |
| US20210025813A1 (en) * | 2018-03-16 | 2021-01-28 | Keio University | Infrared analysis system, infrared analysis chip, and infrared imaging device |
| WO2019206430A1 (en) * | 2018-04-27 | 2019-10-31 | Ecole Polytechnique Federale De Lausanne (Epfl) | Method and spectrometer apparatus for investigating an infrared absorption of a sample |
| CN108444946A (en) * | 2018-05-10 | 2018-08-24 | 苏州农业职业技术学院 | A kind of Practice for Pesticide Residue in Agricultural Products detection method and device |
| CN111426636A (en) * | 2020-04-09 | 2020-07-17 | 米诺杰科技(江苏)有限公司 | Instrument for quickly analyzing chemical component content of wine |
Non-Patent Citations (3)
| Title |
|---|
| 李波: "基于人工电磁表面的新型天线技术研究", 《中国优秀博士学位论文全文数据库基础科学辑》 * |
| 郝雨凡 等: "高灵敏检测传感芯片应用于脑胶质瘤疾病检测", 《红外与激光工程》 * |
| 陈晨 等: "玻璃衬底二氧化钒薄膜的宽频带太赫兹波调制特性", 《强激光与粒子束》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023224859A1 (en) * | 2022-05-16 | 2023-11-23 | The Regents Of The University Of California | Neural network enabled disease spectroscopy |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106841103A (en) | Near infrared spectrum detects fruit internal quality method and dedicated test system | |
| EP3729053B1 (en) | Fast and robust fourier domain-based cell differentiation | |
| CN110378374A (en) | A kind of tealeaves near infrared light profile classification method that fuzzy authentication information extracts | |
| Pan et al. | Identification of complex mixtures for Raman spectroscopy using a novel scheme based on a new multi-label deep neural network | |
| CN113390814A (en) | Intelligent component analysis system and method based on metamaterial spectrometer chip | |
| Xu et al. | Microplastic characterization by infrared spectroscopy | |
| Ebere et al. | Microplastics, an emerging concern: A review of analytical techniques for detecting and quantifying microplatics | |
| Hussain et al. | Rapid detection system for hepatitis B surface antigen (HBsAg) based on immunomagnetic separation, multi-angle dynamic light scattering and support vector machine | |
| Hanson et al. | Slurp! spectroscopy of liquids using robot pre-touch sensing | |
| CN105911000A (en) | Characteristic wave band based blood spot egg on-line detection method | |
| CN117092050B (en) | Coal slime flotation ash content detection method and system based on spectrum multi-mode time sequence learning | |
| Cai et al. | Online detection of concentrate grade in the antimony flotation process based on in situ Raman spectroscopy combined with a CNN-GRU hybrid model | |
| Abimbola et al. | In-situ detection of microplastics in the aquatic environment: A systematic literature review | |
| CN107870164A (en) | A kind of material detection system and application method based on laser Induced Fluorescence Technology | |
| CN116858822A (en) | Quantitative analysis method for sulfadiazine in water based on machine learning and Raman spectrum | |
| CN115718089A (en) | Method for rapidly identifying sample category based on flora Raman features | |
| CN110426366A (en) | Meat adulteration ratio detection method based on visualization olfactory sensor and near-infrared | |
| CN208476785U (en) | A kind of laser induced breakdown spectroscopy detection device suitable for aquatic products heavy metal analysis | |
| CN110887798A (en) | Nonlinear full-spectrum water turbidity quantitative analysis method based on extreme random tree | |
| CN115078327A (en) | Rapid detection method for dangerous chemicals based on neural network architecture search | |
| CN108986096A (en) | A kind of mixed oil liquid discrimination method based on three-dimensional fluorescence spectrum Yu Tchebichef square | |
| CN112326619A (en) | Micro-fluidic pesticide residue detection method based on double-spectrum technology | |
| CN105067575A (en) | Method for detecting mercury in water based on quantum dot fluorescence probe, and apparatus thereof | |
| Maffezzoli et al. | Detection of ice core particles via deep neural networks | |
| CN103389295A (en) | Detection method for Raman spectroscopic data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |